© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19242
    Prev
    Next
    INDEX
    Explanations

    creative activities and projects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ಗಾ
    0.48
    ਘ
    0.48
    guid
    0.44
     fucking
    0.44
     infrequent
    0.43
     solit
    0.42
     moderately
    0.42
    юм
    0.41
     fuck
    0.40
    ɻ
    0.40
    POSITIVE LOGITS
     themed
    0.49
    themed
    0.46
     फर्जी
    0.44
     poetry
    0.44
     Poetry
    0.44
     imaginary
    0.44
    调查
    0.42
     Sensory
    0.42
     empathy
    0.42
     scavenger
    0.42
    Activations Density 0.065%

    No Known Activations